AgentGid
Live data on AI agents, APIs and models: prices, free tiers, limits, outages, real-world usage.
Should I use this
Quality & Safety
Findings (1)
- LOWTool 'get_api' description lacks action verbin get_api
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"agentgid": {
"url": "https://agentgid.com/mcp"
}
}
}Remote endpoints
https://agentgid.com/mcpstreamable-httpWhat it can do
Tool inventory
Tools (16)
🟢find_tools(goal, limit)
Search AgentGid for agents, coding tools, APIs, models and stacks that fit a goal, e.g. 'Solana LP copy-trading bot', 'web search API for a research agent under $50/month', 'generate 3D models for a game'. Returns candidates grouped by kind with prices, free tiers and links. Use this first, then get_api / get_agent for details.
Input Schema
{
"type": "object",
"properties": {
"goal": {
"description": "What the user wants to build or do, in plain words",
"type": "string"
},
"limit": {
"default": 12,
"maximum": 30,
"minimum": 3,
"type": "integer"
}
},
"required": [
"goal"
]
}🟢list_api_categories
List the categories of APIs for agents AgentGid compares (web search, scraping, sandboxes, memory, vector DBs, LLM gateways, email, voice, payments, blockchain RPC, DEX swap, crypto data, 3D, image, audio, video generation).
Input Schema
{
"type": "object",
"properties": {}
}🟢find_apis(category, chain, free_tier_only, max_price_per_1k, mcp_only)
Compare APIs in one category on official price, free tier, MCP support, SDK downloads and status. Filters are optional.
Input Schema
{
"type": "object",
"properties": {
"category": {
"description": "Category slug from list_api_categories, e.g. web-search, blockchain-rpc, 3d-generation",
"type": "string"
},
"chain": {
"description": "For crypto APIs, e.g. Solana",
"type": "string"
},
"free_tier_only": {
"type": "boolean"
},
"max_price_per_1k": {
"description": "Max USD per 1,000 requests (only APIs with a per-request price)",
"type": "number"
},
"mcp_only": {
"description": "Only APIs with an official MCP server",
"type": "boolean"
}
},
"required": [
"category"
]
}🟢get_api(api)
Full details of one API: pricing (free tier, plans, usage price, notes), SDK packages, MCP server, status, cheaper alternatives.
Input Schema
{
"type": "object",
"properties": {
"api": {
"description": "API slug or name, e.g. tavily, helius, meshy",
"type": "string"
}
},
"required": [
"api"
]
}🟢get_agent(agent)
Details of an AI agent or developer tool (Claude Code, Cursor, Codex, Copilot, Headroom ...): pricing, plan usage limits, live status and incidents, latest release, popularity, safety settings.
Input Schema
{
"type": "object",
"properties": {
"agent": {
"description": "Agent slug or name",
"type": "string"
}
},
"required": [
"agent"
]
}🟢check_status(names)
Live status of agents and APIs from their official status pages, with incidents in the last 30 days.
Input Schema
{
"type": "object",
"properties": {
"names": {
"items": {
"type": "string"
},
"maxItems": 20,
"type": "array"
}
},
"required": [
"names"
]
}🟢model_prices(limit, query)
API prices of LLMs (per 1M input/output tokens, context) and which agents can use them. Optional filter by name.
Input Schema
{
"type": "object",
"properties": {
"limit": {
"default": 15,
"maximum": 40,
"type": "integer"
},
"query": {
"type": "string"
}
}
}🟢real_world_usage(agent, domain)
From public GitHub repos set up for AI coding agents: the MCP servers developers connect (overall or per agent), common combinations, and per domain (Solana bots, EVM apps, games, agent products, mobile) the APIs, SDKs and packages they use.
Input Schema
{
"type": "object",
"properties": {
"agent": {
"description": "Optional: claude-code, cursor or github-copilot",
"type": "string"
},
"domain": {
"description": "Optional: solana, evm, games, agent-apps, mobile — what those projects use",
"type": "string"
}
}
}🟢current_deals(agent, kind)
Active official offers from the makers of AI agents and tools: discounts, free access, extra usage, credits, student, startup and open-source programs. Each comes from the vendor's own page, with its end date and source.
Input Schema
{
"type": "object",
"properties": {
"agent": {
"description": "Optional: agent or vendor, e.g. claude-code, cursor, OpenRouter",
"type": "string"
},
"kind": {
"description": "Optional: usage_boost, discount, free_access, credits, student, startup, open_source",
"type": "string"
}
}
}🟢limit_resets(product)
When Anthropic and OpenAI last reset the 5-hour and weekly usage limits of Claude Code and Codex, how often they do it, and recent resets with a link to each announcement.
Input Schema
{
"type": "object",
"properties": {
"product": {
"description": "Optional: claude-code or codex (default both)",
"type": "string"
}
}
}🟢price_history(agent)
How an agent's plans and prices changed month by month, read from archived copies of its official pricing page.
Input Schema
{
"type": "object",
"properties": {
"agent": {
"description": "Agent slug or name, e.g. cursor, claude-code",
"type": "string"
}
},
"required": [
"agent"
]
}🟢find_assets(category, free_commercial_only, query)
Sources of stock photos, video, music, voiceover, 3D models, textures, icons and fonts for apps and agents: price, whether the license allows commercial use and needs credit, and how an agent connects (MCP, API, package, download).
Input Schema
{
"type": "object",
"properties": {
"category": {
"description": "Optional category, e.g. stock-photos, music, voiceover, 3d-models, icons, fonts",
"type": "string"
},
"free_commercial_only": {
"description": "Only sources whose free plan allows commercial use",
"type": "boolean"
},
"query": {
"description": "Optional words to match in the name or description",
"type": "string"
}
}
}🟢find_skills(limit, query)
Agent Skills packs (SKILL.md) for Claude Code, Codex, Cursor and other agents that read skills, from public GitHub repos: what the pack covers, number of skills, stars and the AgentGid page with install commands.
Input Schema
{
"type": "object",
"properties": {
"limit": {
"type": "integer"
},
"query": {
"description": "What the skills should help with, e.g. frontend design, pdf, testing",
"type": "string"
}
},
"required": [
"query"
]
}🟢list_recipes
List the project types AgentGid has a tested kit for (a 2D browser platformer, an interactive 3D web scene, a short-video pipeline, video and audio to text, a PDF tool...): id, title, the questions that shape the kit, and when it was test-built by a coding agent.
Input Schema
{
"type": "object",
"properties": {}
}🟢plan_project(add, answers, files, goal, on, ...)
Get a project kit: one part per job from AgentGid's catalogs (with version, license and reasons), install lines, checks, and with files=true the AGENTS.md brief, CREDITS.md, first prompt and MCP setup files. Give a recipe id from list_recipes or the goal in plain words. If no recipe fits the goal, it says so and lists the recipes: it never improvises a stack.
Input Schema
{
"type": "object",
"properties": {
"add": {
"description": "Add up to 8 parts from AgentGid's catalogs that the recipe does not list: item ids such as \"tool:pikepdf\" or {\"item\": id, \"stage\": \"agent|build|check|ship\"}. They are checked against the answers like every part and marked as added in the files.",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "object"
}
]
},
"type": "array"
},
"answers": {
"description": "Answers by question id, e.g. {\"use\": \"commercial\", \"budget\": \"free\", \"agent\": \"cursor\", \"style\": \"pixel\"}",
"type": "object"
},
"files": {
"description": "Also return the texts of AGENTS.md, CREDITS.md, first-prompt.txt, install.txt and setup files",
"type": "boolean"
},
"goal": {
"description": "What to build, in plain words, e.g. 'a Mario-style browser game'",
"type": "string"
},
"on": {
"description": "Switch parts on or off: {role id: true|false}. Optional parts start off. Assets, agent skills and MCP servers can be switched off, and the brief then says they were removed; parts the plan is built on (libraries, runtimes, services) can only be swapped through picks",
"type": "object"
},
"packs": {
"description": "Choose a pack, model or font inside a picked source: {role id: item id}",
"type": "object"
},
"picks": {
"description": "Swap a part: {role id: item id}, ids as in a previous answer's parts[].pick and alternatives",
"type": "object"
},
"prompt": {
"description": "First prompt: stop after each step (default) or run the whole plan",
"enum": [
"step",
"auto"
],
"type": "string"
},
"recipe": {
"description": "Recipe id from list_recipes, e.g. 2d-platformer",
"type": "string"
}
}
}🟢report_kit_issue(recipe, text, version)
Tell AgentGid's editors what was wrong, missing or out of date in a kit's AGENTS.md after you built from it: a command that failed, a version that did not install, a step that did not work. Only the editors read it; it is never published. Leave out keys, personal data and the person's code.
Input Schema
{
"type": "object",
"properties": {
"recipe": {
"description": "The recipe id from the brief's first lines, e.g. mcp-server (a draft's id starts with draft-)",
"type": "string"
},
"text": {
"description": "What happened and where: the brief's line, the command and its output, and what worked instead",
"type": "string"
},
"version": {
"description": "The recipe version from the same line, e.g. 0.3",
"type": "string"
}
},
"required": [
"recipe",
"text"
]
}Community
Evidence